Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    EE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Netflix
    -0.08
    AGAIN
    -0.07
     zamanda
    -0.07
     Accident
    -0.07
     Frontier
    -0.06
     düzey
    -0.06
    τικές
    -0.06
     accident
    -0.06
     Written
    -0.06
     Pyongyang
    -0.06
    POSITIVE LOGITS
    .eclipse
    0.08
    .ejb
    0.07
    244
    0.07
    ато
    0.07
    oustic
    0.06
    PET
    0.06
     TI
    0.06
    limitations
    0.06
    \E
    0.06
    -pre
    0.06
    Act Density 0.001%

    No Known Activations